Process treatment device diagnostic device, diagnostic system, and diagnostic method

Abstract

The objective of the present invention is to provide a technology for suppressing false alarms generated for, and enabling efficient countermeasures for, a component whose status is measured by a plurality of sensors or for each component of a process treatment device group in the diagnosis of process treatment device deterioration. To this end, a process treatment device diagnostic device according to the present invention is for maintaining the components of a process treatment device and comprises: a feature change computation unit that calculates deterioration degrees corresponding to change indicators from features of respective sensor waveform data for sensor items for a plurality of sensors (status sensor group) that measure the status of the components; and a component deterioration degree computation unit that uses the plurality of degradation degrees to compute component deterioration degrees that correspond to the components in a one-to-one manner.

Description

Diagnostic device, diagnostic system, and diagnostic method for process processing device

[0001] The present invention relates to a diagnostic device, a diagnostic system, and a diagnostic method for a process processing device that processes semiconductor wafers.

[0002] Process processing equipment is a device that performs processing to form microscopic features on semiconductor wafers. In process processing equipment, maintenance work such as replacing and cleaning components that require maintenance is typically performed periodically, based on the number of wafers processed. However, unplanned maintenance work can occur due to component deterioration caused by aging or the accumulation of reaction by-products depending on usage. In order to reduce downtime due to unplanned maintenance, it is necessary to continuously monitor the deterioration state of components and take early measures such as cleaning or component replacement depending on the deterioration state.

[0003] To achieve such early countermeasures, a diagnostic device for a process processing equipment first calculates feature quantities that indicate the characteristics of the sensor waveform data using sensor waveform data, which is a time-series signal consisting of multiple sensor items sequentially acquired for each process operation from multiple status sensors attached to the components of the process processing equipment (the data items of the sensor waveform data are called sensor items).Furthermore, based on the feature quantities, a deterioration level that indicates the deterioration state of the component is estimated from the deviation from the normal state, and the degree is compared with a preset alarm threshold to determine whether maintenance is required and issue an alarm.

[0004] Regarding diagnostic processing of process processing equipment, for example, International Publication No. 2018 / 061842 (Patent Document 1) states, "An anomaly detection device applies statistical modeling to a summary value that summarizes observed values, thereby inferring a state in which noise has been removed from the summary value, and generates a predicted value that predicts the summary value one period ahead based on the inference. The anomaly detection device detects the presence or absence of an anomaly in the monitored equipment based on the predicted value." Furthermore, Japanese Patent Application Laid-Open No. 2012-9064 (Patent Document 2) states, "A learning-type process anomaly diagnosis device that achieves accurate anomaly detection and anomaly diagnosis performance appropriate for practical process monitoring." These prior art technologies are, so to speak, individual approaches that statistically process waveform data from each sensor individually and estimate deterioration by comparing the predicted value with the current value.

[0005] International Publication No. 2018 / 061842 Japanese Patent Application Laid-Open No. 2012-9064

[0006] However, in the diagnosis of process processing equipment, the following factors are thought to cause false alarms in the diagnosis of deterioration in prior art, making it difficult to take efficient measures based on the diagnosis results. First, in process processing equipment, the state of the equipment components changes depending on the processing history, so false alarms can occur due to differences in the initial state between the components in the process processing equipment group. Diagnosis using an individual approach such as that described in Patent Documents 1 and 2 does not, in the first place, provide any recognition of issues that address variations between the components in the process processing equipment group.

[0007] Second, false alarms may occur due to the setting of alarm thresholds. When thresholds are set based on the operator's past knowledge, the occurrence of false alarms depends on the operator's experience. In addition, thresholds may be set by setting a control standard, such as 3σ, to account for the variation in the characteristic values ​​of each sensor in each process processing equipment under normal conditions. In this case, since a process processing equipment is equipped with a variety of sensors, and because they are subject to mutual interference due to control and to the equipment condition, it is rare for the outputs of all sensor items to be stable. Therefore, when diagnosing deviations from the normal state for various sensor items, false alarms may occur frequently. Furthermore, when thresholds are set based on sensor values ​​at the time of a degradation event, the setting itself is difficult because degradation events occur relatively infrequently. Diagnosis using an individual approach, such as those described in Patent Documents 1 and 2, does not recognize the issues involved in setting thresholds for degradation states that correspond to differences in equipment and various sensor items.

[0008] Third, because multiple sensors attached to components of a process processing device interfere with each other, in methods of diagnosing based on feature values ​​calculated for each sensor, such as the individual approaches of Patent Documents 1 and 2, the diagnostic results for each sensor may not necessarily be directly related to the degradation state of the component, which may lead to false alarms. Therefore, an object of the present invention is to provide a technology that, in diagnosing degradation of a process processing device, suppresses false alarms generated for components whose states are measured by multiple sensors or for each component of a group of process processing devices, and enables efficient countermeasures.

[0009] In order to solve the above-mentioned problems, one representative diagnostic device for a process processing device of the present invention is a diagnostic device for a process processing device that performs maintenance on components of the process processing device, and includes: a feature change calculation unit that calculates a deterioration degree corresponding to a change index from feature values ​​of sensor waveform data of each sensor item for a plurality of sensors (a group of status sensors) that measure the status of the component; and a component deterioration degree calculation unit that calculates a component deterioration degree that corresponds one-to-one to the component using the plurality of deterioration degrees.

[0010] According to the present invention, it is possible to provide a technology that can suppress false alarms generated for components whose states are measured by multiple sensors or for each component of a group of process processing devices in diagnosing deterioration of the process processing device, and enable efficient countermeasures. Problems, configurations, and effects other than those described above will become clear from the description of the following embodiments.

[0011] FIG. 1 is a diagram showing the overall configuration of a process processing device and a diagnostic device for the process processing device. FIG. 2 is a relationship diagram showing the positioning of component deterioration levels and device-common thresholds, etc. FIG. 3 is a flowchart showing an example of the processing flow in the computer 30. FIG. 4 is a flowchart showing an example of the processing flow in the server 50. FIG. 5 is a diagram for explaining an example of a device-common threshold setting method. FIG. 6 is a diagram showing an example of a display screen in the diagnostic result display unit 512.

[0012] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In all drawings for explaining the embodiments, the same parts are generally designated by the same reference numerals, and repeated description thereof will be omitted.

[0013] (Process Processing Apparatus) FIG. 1 is a diagram showing the overall configuration of a process processing apparatus and a diagnostic apparatus for the process processing apparatus. As shown in FIG. 1, process processing apparatus A (10), process processing apparatus B (11), and the like that constitute a process processing apparatus group 1 in this embodiment process wafers (samples 101) according to preset process processing conditions. Each process processing apparatus is equipped with the same type of components, and each component is equipped with a status sensor group 102 consisting of multiple sensors that measure the status of the component. Measured values ​​of the sensor (e.g., temperature and pressure) during processing or idle can be acquired as sensor waveform data. Examples of the process processing apparatus, component, and status sensor include a plasma processing apparatus, a microwave generation unit, and a current / voltage sensor, respectively.

[0014] (Diagnostic Apparatus) As shown in FIG. 1 , the diagnostic apparatus 2 includes a group of computers (computers 30, 40, . . . ) consisting of an execution unit 31 that acquires sensor waveform data corresponding to each process processing device in the process processing apparatus group 1 and performs calculations, and a storage unit 32 that stores information required for the execution unit's processing. Furthermore, the diagnostic apparatus 2 includes an analysis unit 51 that sets calculation conditions and device-wide thresholds for the execution unit 31 and displays diagnostic results, and a server 50 that stores information required for the analysis unit 51's processing. The process processing apparatus group 1 is connected to the group of computers (computers 30, 40, . . . ) directly or via a network. Furthermore, the group of computers (computers 30, 40, . . . ) and the server 50 are connected via a network. This allows each computer to perform high-speed calculations using sensor waveform data acquired from each process processing device in the execution unit 31. Furthermore, the server 50 can set calculation conditions and thresholds across the process processing apparatus group 1, and analyze and display diagnostic results. However, the connection between the group of computers and the server 50 is not necessarily limited to a network, and they may be directly connected by processing devices.

[0015] (Computer) The execution unit 31 is composed of a processor such as a CPU or GPU, and as will be described later, includes a preprocessing unit 310, a feature amount change calculation unit 311, a diagnosis and reporting unit 312, a feature amount calculation unit 313, and a component deterioration level calculation unit 314. The storage unit 32 is composed of a memory, a hard disk, etc., and as will be described later, includes a sensor waveform storage unit 320 and a calculation result storage unit 321.

[0016] (Server) The analysis unit 51 is composed of a processor such as a CPU or GPU, and includes a calculation condition setting unit 510, a device-common threshold setting unit 511, and a diagnosis result display unit 512, as will be described later. The storage unit 52 is composed of a memory, a hard disk, etc., and includes a diagnosis result storage unit 520 and a maintenance timing information storage unit 521, as will be described later.

[0017] FIG. 2 is a diagram showing the relationship between component deterioration levels and equipment-wide thresholds. A process processing device has one or more components, each of which is equipped with multiple sensors (a group of status sensors). One or more feature values ​​are calculated for each sensor item, and one or more deterioration levels are calculated for each feature value. In this way, a component deterioration level that corresponds one-to-one to the component is calculated from the multiple deterioration levels obtained from a single component. Furthermore, an equipment-wide threshold that serves as a standard for deterioration detection is set from the component deterioration levels for components of the same type that are provided in multiple process processing devices (a group of process processing devices).

[0018] (Processing by Computer) An example of a diagnostic process for the degradation state of each component of the process processing device 10 performed by the computer 30 will be described. Fig. 3 is a flowchart showing an example of the flow of processing by the computer 30. Fig. 3 shows the flow of processing for each diagnostic period. The diagnostic period may be, for example, for each process or at regular time intervals.

[0019] First, the computer 30 acquires sensor waveform data for a diagnostic period from the sensor waveform storage unit 320. The sensor waveform data is configured so that sensor values ​​for each of a plurality of sensor items are stored in a time series, such as processing time or time. The preprocessing unit 310 then selects one sensor item from the sensor waveform data (S1). Next, the preprocessing unit 310 preprocesses the sensor waveform data for the selected sensor item (S2). While any preprocessing method may be used, for example, a process ID, which is information for identifying process conditions, may be used to specify the process ID to be used for diagnosis, and the associated sensor waveform data may be extracted. The processing time interval to be used for diagnosis may also be extracted, and missing values ​​may be removed and standardized to make the data easier to handle.

[0020] Next, the feature calculation unit 313 calculates feature quantities that indicate the characteristics of the sensor waveform data using the preprocessed sensor waveform data (S3). As shown in FIG. 2, one or more feature quantities are calculated for each sensor item. For example, statistical quantities such as the mean value or standard deviation of the sensor waveform data can be used as feature quantities. For example, in a plasma processing apparatus, the mean value over a specific time period can be used as a feature quantity for current waveform data. A feature quantity that is highly likely to be related to degradation may be calculated by matching it with domain knowledge of the component, or multiple feature quantities may be calculated. Next, the feature change calculation unit 311 determines whether the initial state period has expired (S4). The initial state period refers to the time interval from immediately after maintenance work on the component to a certain period. If the initial state period has not expired in the diagnostic cycle at the time of determination, the preprocessing unit 310 determines whether feature calculation has been completed for all sensor items for which feature calculation is to be performed (S6). If the calculation has been completed, the processing for that diagnostic cycle ends. If the calculation has not been completed in S6, the processing moves to selecting another sensor item and continues.

[0021] In S4, if the initial state interval is exceeded, the feature change calculation unit 311 calculates a deterioration level for each calculated feature by taking the change from the initial state (S5). The deterioration level is calculated for each feature using multiple change indices. Examples of change indices include the difference or ratio between the average feature value in the initial state interval and the feature value in the current diagnostic cycle, or the Mahalanobis distance between the feature value in the initial state interval and the feature value in the current diagnostic cycle. In this way, by defining the deterioration level based on the change from the initial state in each process processing device of the process processing device group 1, deterioration levels can be compared between process processing devices. Furthermore, because the change indices to be compared depend on the sensor item, multiple change indices are defined, and multiple deterioration levels are calculated based on them. For example, if the change from the initial state is a significant physical quantity, the difference is considered to be an effective change indices, and if the rate of change is a significant physical quantity, the ratio is considered to be an effective change indices. Furthermore, if a feature value exhibits significant variability even in the initial state, the Mahalanobis distance, which takes variability into account, is considered to be effective. Next, the component deterioration level calculation unit 314 proceeds to determine whether the calculation of the deterioration level for all sensor items has been completed (S7), and if not, repeats the same process for another sensor item, and if completed, proceeds to processing in S8.

[0022] In S8, the component degradation level calculation unit 314 calculates an index that integrates the multiple calculated degradation levels for each component as a component degradation level. The contribution of each degradation level to the component degradation level is also calculated. The calculation conditions for the component degradation level are calculated in the calculation condition setting unit 510, and an example of the calculation method will be described later. It is assumed that degradation of a process processing device component may be caused by multiple degradation factors, or that a single degradation factor may affect the degradation state of multiple sensor items. A comprehensive approach using the component degradation level calculated from individual degradation levels enables calculation and diagnosis of the degradation level that takes into account the interactions between multiple sensor items. Next, the diagnosis / reporting unit 312 determines whether the calculation of the component degradation level for all components to be diagnosed has been completed, and repeats the calculation until completion (S9).

[0023] Finally, the diagnosis and alarm issuing unit 312 compares the calculated component deterioration level for the current diagnosis cycle with the device-wide threshold set in advance by the device-wide threshold setting unit 511 for each component, and if the calculated component deterioration level exceeds the device-wide threshold, it notifies the server 50 of the issuance of an alarm (S10).

[0024] (Processing in Server) An example of processing performed by the server 50 to set the calculation conditions and device-common thresholds in the computer 30 will be described. Fig. 4 is a flowchart showing an example of the flow of processing in the server 50. The processing flow for setting the calculation conditions and device-common thresholds may be performed whenever it becomes necessary to set or update new calculation conditions or device-common threshold values.

[0025] First, in the calculation condition setting unit 510, for a component of interest, the calculation result of the deterioration degree in the process processing device group 1 and the maintenance timing information are obtained from the calculation result storage unit 321 and the maintenance timing information storage unit 521, respectively (T1). The maintenance timing information includes history information such as the timing and content of maintenance performed in response to deterioration of the component of each process processing device.

[0026] Next, in the calculation condition setting unit 510, for the process processing equipment of interest, the deterioration level in the maintenance interval section is extracted from the time-series deterioration level trend calculated by the computer 30 for each diagnostic period based on the maintenance timing information (T2). As a result, the left end of the time-series deterioration level trend represents the initial state, and the right end represents the deterioration state. Since the computer 30 calculates multiple deterioration levels, multiple time-series deterioration level trends also exist. Note that for process processing equipment that does not include maintenance timing information, i.e., new process processing equipment or process processing equipment that is currently in use after maintenance (no deterioration events have occurred), the deterioration level trend from the initial state to the most recent calculation point is extracted. Because deterioration events occur relatively rarely, utilizing data from process processing equipment that does not include maintenance timing information is effective in reducing false alarms.

[0027] Next, the calculation condition setting unit 510 calculates the component degradation level using the time-series trends of the multiple degradation levels (T3). Various methods for calculating the component degradation level are possible. For example, a model for calculating the component degradation level can be constructed by applying a machine learning technique including a decision tree structure. When constructing the model, a model is created using each degradation level trend as an explanatory variable and the degradation time as a target variable, and the model parameters are optimized according to the data. From the perspective of narrowing down the effective feature values ​​for each sensor item, a machine learning technique with a feature selection function may be used to select one degradation level for each sensor item, as shown in FIG. 2, and then calculate the component degradation level. Furthermore, from the perspective of interpretability of the diagnosis results, it is desirable to use a model that can calculate the contribution of each degradation level to the component degradation level. Multiple models may also be constructed. The equipment-common threshold setting unit 511 determines whether the calculation is complete for all process processing devices to be diagnosed, and repeats the processes from T2 to T3 for each process processing device to calculate the component degradation level of the component of interest (T4).

[0028] Next, the equipment-common threshold setting unit 511 sets a common threshold for each component degradation level across the process processing equipment group 1 (T5). FIG. 5 is a diagram illustrating an example of an equipment-common threshold setting method. FIG. 5 shows a state in which a time-series trend of component degradation levels is calculated across the process processing equipment group 1. The set thresholds are comprehensively scanned, and a common threshold is set across the equipment so as to maximize the prediction accuracy index for the desired degradation time. To suppress false alarms, for example, the recall rate under conditions where the precision rate is equal to or greater than a reference value is used as the prediction accuracy index. If multiple component degradation level calculation models are constructed in T3, the component degradation level calculation model to be used for diagnosis by the computer 30 is selected based on the prediction accuracy index. This comprehensive approach of setting equipment-common thresholds to optimize the prediction accuracy index makes it possible to suppress false alarms caused by individual factors within the equipment.

[0029] Finally, the calculation condition setting unit 510 sets the selected component deterioration level calculation model (calculation condition) and the inter-device common threshold as conditions to be used for diagnosis in the computer 30 (T6). Next, the calculation condition setting unit 510 determines whether the settings are complete for all components to be diagnosed, repeats the processes from T1 to T6 (T7), and ends the process.

[0030] FIG. 6 is a diagram showing an example of a display screen in the diagnosis result display unit 512. As shown in FIG. 6( a), the time-series trends of component degradation and common thresholds among devices can be displayed at a glance for all components to be diagnosed in the process processing equipment group 1. This allows users to see at a glance which components in which process processing equipment are most likely to be in a degraded state. Furthermore, if an error of unknown cause occurs in a process processing equipment, efficient countermeasures can be implemented by prioritizing maintenance work on components most likely to be in a degraded state. Furthermore, as shown in FIG. 6( b), by specifying a component ID, the contribution of each degradation level (degradation level calculation condition) to the component degradation level can be confirmed. This provides supplementary information for factor estimation by comparing with domain knowledge of the component, enabling efficient countermeasures.

[0031] Although the embodiment has been described above, the present invention is not limited to the above embodiment and various modifications are possible without departing from the spirit of the present invention. For example, if it is difficult to install the server 50, the computer 30 may be configured to perform part of the processing of the server 50.

[0032] The following are examples of aspects that may be included in the present invention, but the present invention is not limited to these. (Aspect 1) A diagnostic device for a process processing device for performing maintenance on a component of the process processing device, comprising: a feature amount change calculation unit that calculates a deterioration level corresponding to a change index from feature amounts of waveform data of each sensor item corresponding to a plurality of sensors (a group of status sensors) that measure the status of the component; and a component deterioration level calculation unit that calculates a component deterioration level that corresponds one-to-one to the component using the plurality of deterioration levels. (Aspect 2) The diagnostic device for a process processing device according to Aspect 1, further comprising a diagnosis and reporting unit that diagnoses and reports by comparing the component deterioration level with a device-common threshold set among the components of the group of process processing devices. (Aspect 3) The diagnostic device for a process processing device according to Aspect 1 or 2, characterized in that the feature amount change calculation unit uses, as the change index, at least one of the difference between the feature amount in a diagnostic cycle and an average value of the feature amount in an initial state section of the component (hereinafter referred to as "initial feature amount"), the ratio to the average value of the initial feature amount, or the Mahalanobis distance from the average value of the initial feature amount. (Aspect 4) The diagnostic device for process processing equipment according to any one of Aspects 1 to 3, wherein the component degradation level calculation unit calculates the component degradation level as a continuous probability value using a technique for applying a regression model including a decision tree structure. (Aspect 5) The diagnostic device for process processing equipment according to Aspect 2, further comprising an equipment-common threshold setting unit that sets the equipment-common threshold by comprehensively searching for a prediction accuracy index of degradation time from a time-series trend of the component degradation level in each component of the group of process processing equipment. (Aspect 6) The diagnostic device for process processing equipment according to Aspect 5, wherein the equipment-common threshold setting unit uses a precision rate and a recall rate as the prediction accuracy index, and sets the equipment-common threshold so that the precision rate is equal to or greater than a reference value and the recall rate is maximized.(Aspect 7) The diagnostic device for a process processing equipment according to any one of Aspects 2, 5, and 6, comprising a diagnostic result display unit that displays a time-series trend of a component degradation degree for each component of the process processing equipment group, together with the contribution degrees of the plurality of degradation degrees used in calculating the component degradation degree. (Aspect 8) A diagnostic system for a process processing equipment for maintaining a component of the process processing equipment, comprising: a feature amount change calculation unit that calculates a degradation degree corresponding to a change index from feature amounts of sensor waveform data of each sensor item for a plurality of sensors (a group of status sensors) that measure the status of the component, and a component degradation degree calculation unit that calculates a component degradation degree in one-to-one correspondence with the component using the plurality of degradation degrees. (Aspect 9) The diagnostic system for a process processing equipment according to Aspect 8, comprising a diagnosis and reporting unit that diagnoses and reports by comparing the component degradation degree with a device-common threshold value set among the components of the process processing equipment group. (Aspect 10) A diagnostic method for a process processing device for maintaining a component of the process processing device, comprising: a step of calculating, in a feature amount change calculation unit, a deterioration degree corresponding to a change index from feature amounts of sensor waveform data of each sensor item for a plurality of sensors (a group of status sensors) that measure the status of the component; and a step of calculating, in a component deterioration degree calculation unit, a component deterioration degree that corresponds one-to-one to the component using the plurality of deterioration degrees. (Aspect 11) The diagnostic method for a process processing device according to Aspect 10, comprising: a step of diagnosing and issuing a report in a diagnosis / reporting unit by comparing the component deterioration degree with a device common threshold value set among each component of a group of process processing devices.

[0033] DESCRIPTION OF SYMBOLS 1... process processing device group, 2... diagnostic device, 10, 11... process processing device 30, 40... computer, 31... execution unit, 32, 52... storage unit, 50... server 51... analysis unit, 310... pre-processing unit, 311... feature amount change calculation unit, 312... diagnosis and reporting unit 313... feature amount calculation unit, 314... component deterioration degree calculation unit 510... calculation condition setting unit, 511... device common threshold setting unit, 512... diagnosis result display unit 520... diagnosis result storage unit, 521... maintenance time information storage unit

Claims

1. A diagnostic device for a process processing device for maintaining components of the process processing device, comprising: a feature change calculation unit that calculates a deterioration level corresponding to a change index from feature values ​​of sensor waveform data of each sensor item for a plurality of sensors (a group of status sensors) that measure the status of the component; and a component deterioration level calculation unit that calculates a component deterioration level that corresponds one-to-one to the component using the plurality of deterioration levels.

2. A diagnostic device for a process processing device as described in claim 1, further comprising a diagnosis and reporting unit which diagnoses and reports by comparing the component deterioration degree with a common threshold value set among each component of a group of process processing devices.

3. A diagnostic device for a process processing device as described in claim 1 or 2, characterized in that the feature change calculation unit uses as the change index at least one of the difference between the feature in a diagnostic cycle and the average value of the feature in an initial state section of the component (hereinafter referred to as "initial feature"), the ratio to the average value of the initial feature, or the Mahalanobis distance from the average value of the initial feature.

4. A diagnostic device for a process processing device as described in claim 1 or 2, characterized in that in the component deterioration level calculation unit, the component deterioration level is calculated as a continuous probability value using a method of applying a regression model including a decision tree structure.

5. A diagnostic device for process processing equipment as described in claim 2, further comprising an equipment common threshold setting unit that sets the equipment common threshold by comprehensively searching for a prediction accuracy index of deterioration time from a time series trend of the component deterioration degree in each component of the group of process processing equipment.

6. The diagnostic device for process processing equipment described in claim 5, characterized in that in the equipment common threshold setting unit, a precision rate and a recall rate are used as the prediction accuracy indexes, and the equipment common threshold is set so that the precision rate is equal to or greater than a reference value and the recall rate is maximized.

7. A diagnostic device for a process processing device as described in any one of claims 2, 5 and 6, further comprising a diagnostic result display unit which displays a time series trend of the component deterioration degree in each component of the process processing device group, together with the contribution degree of the multiple deterioration degrees used in calculating the component deterioration degree.

8. A diagnostic system for a process processing device for maintaining components of the process processing device, comprising: a feature change calculation unit that calculates a deterioration degree corresponding to a change index from feature values ​​of sensor waveform data of each sensor item for a plurality of sensors (a group of status sensors) that measure the status of the component; and a component deterioration degree calculation unit that calculates a component deterioration degree that corresponds one-to-one to the component using the plurality of deterioration degrees.

9. The process processing device diagnostic system according to claim 8, further comprising a diagnostic and reporting unit which diagnoses and reports by comparing the component deterioration level with a common threshold value set among each component of a group of process processing devices.

10. A method for diagnosing a process processing device in which a component of the process processing device is the maintenance target, the method comprising: a step of calculating, in a feature change calculation unit, a deterioration degree corresponding to a change index from the feature of each sensor waveform data of a sensor item for a plurality of sensors (a group of status sensors) that measure the status of the component; and a step of calculating, in a component deterioration degree calculation unit, a component deterioration degree that corresponds one-to-one to the component using the plurality of deterioration degrees.

11. A method for diagnosing a process processing device as described in claim 10, comprising a step of diagnosing and issuing a report in a diagnosis / reporting unit by comparing the degree of deterioration of the component with a common threshold value set among each component of a group of process processing devices.

Images